© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 1849
    Prev
    Next
    INDEX
    Explanations

    future-oriented verbs and phrases indicating expectation or prediction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Comes before "be appreciated" or "will recognize."

    np_acts-logits-general · gemini-2.0-flash

    will be appreciated or recognize

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     חיצוניים
    -0.60
    Datuak
    -0.53
     AssemblyTitle
    -0.53
     mir
    -0.50
    FieldBuilder
    -0.49
     ചെയ
    -0.49
     kali
    -0.49
    不通
    -0.48
    ">//
    -0.48
    المناصب
    -0.48
    POSITIVE LOGITS
     HttpNotFound
    0.70
    localctx
    0.56
     hoped
    0.53
     familiar
    0.53
    ScopeManager
    0.53
     BoxFit
    0.53
    andExpect
    0.52
     hoffe
    0.52
     bristle
    0.52
    Surely
    0.52
    Activations Density 0.248%

    No Known Activations